WO2020212061A1 - Procédé de prédiction d'une situation de circulation routière pour un véhicule - Google Patents

Procédé de prédiction d'une situation de circulation routière pour un véhicule Download PDF

Info

Publication number
WO2020212061A1
WO2020212061A1 PCT/EP2020/057501 EP2020057501W WO2020212061A1 WO 2020212061 A1 WO2020212061 A1 WO 2020212061A1 EP 2020057501 W EP2020057501 W EP 2020057501W WO 2020212061 A1 WO2020212061 A1 WO 2020212061A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
prediction
traffic situation
prediction parameters
automated
Prior art date
Application number
PCT/EP2020/057501
Other languages
German (de)
English (en)
Inventor
Florian Wirthmüller
Jochen Hipp
Joachim Herbst
Original Assignee
Daimler Ag
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Daimler Ag filed Critical Daimler Ag
Priority to US17/602,354 priority Critical patent/US11945450B2/en
Priority to CN202080029414.0A priority patent/CN113728369B/zh
Publication of WO2020212061A1 publication Critical patent/WO2020212061A1/fr

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/164—Centralised systems, e.g. external to vehicles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/0097—Predicting future conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/04—Monitoring the functioning of the control system
    • B60W50/045—Monitoring control system parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/165—Anti-collision systems for passive traffic, e.g. including static obstacles, trees
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0062—Adapting control system settings
    • B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
    • B60W2050/0083—Setting, resetting, calibration
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/45—External transmission of data to or from the vehicle

Definitions

  • the invention relates to a method for predicting a traffic situation for a vehicle according to the preamble of claim 1.
  • the invention further relates to a method for operating an automated,
  • Movement hypothesis trajectories of the vehicles are generated, with position data of the vehicles, movement data of the vehicles and, as a function of driver intentions of both drivers, in a first method stage
  • Movement leeway between the vehicles are determined and the probability of danger is determined as a function of a size of the respective movement leeway.
  • the invention is based on the object of specifying a novel method for predicting a traffic situation for a vehicle. Furthermore, the invention is based on the object of specifying a novel method for operating an automated, in particular highly automated or autonomously driving vehicle.
  • the object is achieved with a method for predicting a
  • Traffic situation solved which has the features specified in claim 1.
  • the object is further achieved according to the invention with a method for operating a vehicle which has the features specified in claim 8.
  • an environment of the vehicle is continuously recorded and a traffic situation of the vehicle for a future point in time is predicted on the basis of recorded environment data and prediction parameters.
  • Traffic situation compared and determined in the comparison whether there was a prediction error in the prediction. If there is a prediction error, the
  • the method enables exact predictions of trajectories of vehicles in the vicinity of the vehicle even with widely varying framework conditions, so that
  • Driver race control systems and automated driving functions can be implemented that can work and react adequately at least in almost every situation. When predicting the traffic situation, a generalization is made about all of them
  • the trajectory planning is very safe and reliable.
  • the rules required for the actual prediction may not have to apply under given framework conditions, since these framework conditions may have particular effects on the driving behavior of other road users.
  • the method also enables automated driving functions with regard to legal and ethical aspects.
  • the predicted traffic situation is based on a probable movement behavior of other road users in the Surroundings of the vehicle. For example, the prediction is made with a
  • Prediction horizon which is 2 seconds to 5 seconds, so that the prediction can take place for times of less than 2 seconds to times of less than 5 seconds.
  • a prediction error is determined when a deviation determined in the comparison between the current real traffic situation and the predicted traffic situation exceeds a predetermined tolerance value. This enables a more stable, safe and reliable operation of the method and unnecessary changes to the prediction parameters in the event of small deviations are avoided.
  • Prediction parameters provided by a central processing unit external to the vehicle. This enables the prediction parameters to be called up by the vehicle when they are needed. Complex and long-term storage of the prediction data in the vehicle is not necessary. Furthermore, it is ensured that current prediction parameters are always available to the vehicle.
  • a prediction error is present, a data set which includes the data on which the prediction is based, the prediction parameters, the predicted traffic situation and the real traffic situation is transmitted to the central processing unit, and the prediction parameters are determined by the processing unit as a function of the data set corrected.
  • This external correction of the prediction parameters by means of the computing unit enables an effective and central correction, so that hardware expenditure for the vehicle can be minimized. At the same time, it is ensured that current prediction parameters are always available to the vehicle and possibly other vehicles.
  • the correction of the prediction parameters is carried out on the basis of data records generated by means of a large number of vehicles and transmitted to the computing unit. On the basis of a comparison and an evaluation of the data sets from several vehicles, for example, when data sets from several vehicles are available for a location, a particularly high accuracy of the prediction parameters can be ensured, since detection errors of individual vehicles are reliably detected.
  • the correction of the prediction parameters is carried out by means of a learning algorithm, in particular an artificial neural network. This enables a steady
  • vehicles are requested by the vehicle-external central processing unit to transmit a data record to the processing unit at positions marked as critical in the absence of a prediction error, with the data record underlying the prediction, the prediction parameters, the predicted Traffic situation and the real one
  • Traffic situation includes. In this way, when the prediction parameters are corrected, a database is available for error-free predictions.
  • the previously described method for predicting a traffic situation is carried out during an automated journey and the vehicle retrieves the prediction parameters that apply to this section of the route from at least one central processing unit external to the vehicle before traveling on a route section .
  • the method Due to the use of the method for predicting the traffic situation, the method enables the reliable detection of prediction errors and, as a result, exact predictions of trajectories of vehicles in the vicinity of the vehicle in a particularly advantageous manner by comparing the predicted traffic situation and the traffic situation actually recorded at the future time with widely varying framework conditions. In this way, driver assistance systems and automated driving functions can be implemented that can work and react adequately at least in almost every situation. This enables a particularly safe automated operation of the vehicle, it still being possible to enable automated driving functions for vehicles with regard to legal and ethical aspects.
  • the planned trajectory is implemented in automated ferry operation by means of an automatic control and / or regulation of a longitudinal and / or transverse movement of the vehicle in order to achieve a high degree of automation and thus a high level of comfort for vehicle users.
  • FIG. 1 schematically shows a block diagram of a device for operating a
  • FIG. 2 schematically shows a block diagram of a computer unit external to the vehicle
  • FIG. 3 schematically shows a block diagram of a vehicle and one external to the vehicle
  • FIG. 4 schematically shows a sequence of a method for operating a vehicle.
  • FIG. 1 shows a block diagram of a device 1 for operating a vehicle 2 shown in more detail in FIG. 3, the vehicle 2 being designed for an automated, in particular highly automated or autonomous ferry operation.
  • the device 1 For such an automated operation of the vehicle 2, it is necessary to plan a trajectory T of the vehicle 2 as a function of a current and a predicted traffic situation PU.
  • the device 1 comprises a vehicle's own sensor system 1.1, a prediction module 1.2 for predicting the traffic situation PU, a planning module 1.3 for planning the trajectory T, an implementation module 1.4 for implementing the trajectory T, a sensor system buffer 1.5, a communication module 1.6 for communication Via a communication channel 3, a prediction buffer 1.7 and a comparison module 1.8.
  • sensor information I In order to implement an automated driving function of the vehicle 2, current environmental data of the vehicle 2, also referred to as sensor information I, are continuously recorded using the vehicle's own sensor system 1.1.
  • a prediction of the traffic situation PU is continuously carried out using the sensor information I in order to predict for a future point in time, for example for the next 2 seconds to 5 seconds
  • planning module 1.3 is used to plan trajectories T, with a planned trajectory T by intervening in a longitudinal and transverse movement of the
  • Vehicle 2 is implemented by means of the implementation module 1.4.
  • Both the captured environment data, ie the sensor information I, and the predicted environment data, ie the predicted traffic situation PU, are temporarily stored for later evaluation. This intermediate storage takes place for the Sensor information I in the sensor buffer 1.5 and for the predicted traffic situation PU with the associated prediction parameters P in the prediction buffer 1.7. Buffered sensor information I TO can then be called up at the output of the sensor system buffer 1.5 and predicted traffic situations PU TO that are buffered at the output of the prediction buffer 1.7.
  • Traffic situation compared with the traffic situation PU predicted for this point in time by means of the comparison module 1.8.
  • a buffered, predicted traffic situation PU TO which is buffered, is associated with the comparison module 1.8
  • the comparison module 1.8 If the tolerance range lies, the comparison module 1.8 generates a trigger TR, so that a data record D with the real traffic situation, the traffic situation PU predicted for the same point in time, the sensor information I from which the predicted
  • Traffic situation PU was determined, and prediction parameters P on which the prediction was based, by means of the communication module 1.6
  • Communication channel 3 is transmitted to a vehicle-external central processing unit 4, shown in more detail in FIG. 2, for example a so-called backend server.
  • a prediction module 1.2 which cannot include any knowledge of such a special situation or such a location, would now have to assume that the other road users would most likely not run over the marking, whereas a person who is aware of this location or such a situation would do so Already includes experience in its prediction. It is also assumed that secured sensor signals and thus the
  • Sensor information I is error-free.
  • the sensor signals can be faulty more often than usual at certain points and in certain situations, for example due to reflections from wet road surfaces.
  • This unexpected behavior of the other road users or the unexpected faulty sensor signals can lead to prediction errors, an incorrectly predicted traffic situation PU, and consequently to an incorrectly planned trajectory T and thus, in extreme cases, to collisions.
  • By comparing the traffic situation PU predicted for a later point in time with the traffic situation actually ascertained at this later point in time it is possible to identify a prediction error. If the comparison results in a deviation that exceeds a certain tolerance value, there is a prediction error. If the conditions under which the prediction was carried out are also known and the prediction parameters P are known on which the prediction was based, it is possible to do this
  • prediction parameters P such that the prediction error is minimized. For example, if the prediction error occurs at certain times of the day, e.g. B. in the morning during rush hour, in certain places, such. B. motorway exits, in certain situations, such as. B. in traffic jam or rain occurs, the prediction parameters P are corrected for these times of day, locations or situations.
  • Visibility a time of day, the weather, a traffic situation, etc.
  • Figure 2 shows a block diagram of a possible embodiment of a
  • the computing unit 4 comprises a communication module 4.1 for communication with the device 1 via the communication channel 3, a module 4.2 for communication with the device 1 via the communication channel 3, a module 4.2 for communication with the device 1 via the communication channel 3, a module 4.2 for communication with the device 1 via the communication channel 3, a module 4.2 for communication with the device 1 via the communication channel 3, a module 4.2 for communication with the device 1 via the communication channel 3, a module 4.2 for communication with the device 1 via the communication channel 3, a module 4.2 for
  • the computing unit 4 receives the data sets D from a plurality of vehicles 2 each with a real traffic situation, the traffic situation PU predicted for the same point in time, the sensor information I from which the predicted
  • Traffic situation PU was determined, and prediction parameters P on which the prediction was based.
  • the computing unit 4 thus has a large database available.
  • the received data records D are clustered in the processing unit 4 in order to identify areas in which reported prediction errors occur more frequently. Furthermore, the data record D is fed to module 4.2. If an accumulation of prediction errors is found at certain points, the prediction parameters P, which are used for the prediction at these points, are corrected by means of module 4.2 to minimize the prediction errors. The correction is possible because of the received
  • Data records D are known which are the input data of the prediction, which are the output data of the prediction, d. H. the respective predicted traffic situation PU, and how the output data should actually have been, d. H. the for
  • a correction can be made by means of a learning method, for example by means of an artificial neuronal
  • the learning system is given, for example, a number of input variables,
  • the data volumes are divided along this parameter and the data is divided into two parallel learning processes, for example in two separate learning processes
  • Corrected prediction parameters P + are then stored in the parameter memory 4.3 together with the associated sensor information I and the data record D.
  • vehicles 2 are requested by the central processing unit 4 external to the vehicle to send a data record D to the in each case at positions marked as critical in the absence of a prediction error
  • this data record D also comprising the data on which the prediction is based, the prediction parameters P, the predicted traffic situation PU and the real traffic situation.
  • Prediction parameters P a database for error-free predictions available.
  • An automated driving vehicle 2 then calls before a certain one
  • Prediction parameter P for the prediction algorithm from the computing unit 4 and then - as described under Figure 1 - the prediction of
  • a trajectory T the automated ferry operation of the vehicle 2 is then carried out. That is to say, vehicles 2 then ask processing unit 4 any questions that need to be taken into account
  • the vehicles 2 each call parameter adjustments for the respective
  • Prediction component in the current situation such as, for the example of driving over lane markings on freeway entrances, an increase in a lane change probability despite a solid mark.
  • Prediction component is made known by the corrected prediction parameters P + that certain peculiarities are to be expected so that these the
  • the correction of the prediction parameters P can be carried out as follows. It is determined on the basis of many collected data sets D that on one
  • Lane marking to change lanes although this is illegal and contradicts normal driving behavior in such situations. This impermissible exceeding can be detected, for example, by the fact that vehicles 2 of a fleet have both the
  • Computing unit 4 made available. This can be done through the information by adapting their prediction parameters P to the prediction of the movement of the
  • the data records D are collected in the computing unit 4 when it is established in the vehicle 2 that the prediction for one of the other road users at a certain point is poor with the trajectory actually driven
  • This component is formed by the sensor buffer 1.5 and the prediction buffer 1.7.
  • Figure 3 is a block diagram of a vehicle 2 and a vehicle-external
  • Computing unit 4 is shown.
  • the vehicle 2 and the computing unit 4 communicate via the communication channel 3 by means of their respective communication modules 1.6, 4.1.
  • the communication takes place in such a way that the associated current sensor information I is transmitted from the respective vehicle 2 to the computing unit 4 as a function of a currently detected situation. If the comparison module 1.8 has triggered a data record D, this additionally includes information from the sensor system 1.1 as well as the contents of the sensor system buffer 1.5 and the prediction buffer 1.7.
  • Prediction parameter P among other things also special features in the form of
  • FIG. 4 shows a sequence of a possible exemplary embodiment of a method for operating a vehicle 2.
  • a first method step S1 the traffic situation is recorded with the aid of the sensor system 1.1, and in a second method step S2 by the
  • Context information provided to computing unit 4 is performed in a third method step S3, the prediction of the traffic situation PU, in particular by means of vehicle control devices and software implemented on them.
  • the trajectory T is then planned in a fourth method step S4, in particular by means of vehicle control devices and software implemented on them, and in a fifth method step S5, the trajectory T is implemented using appropriate actuators in the implementation module 1.4.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

La présente invention concerne un procédé de prédiction d'une situation de circulation routière (PU) pour un véhicule (2), en particulier pour un véhicule (2) à conduite automatisée. Un environnement du véhicule (2) est détecté en permanence et à l'aide des données d'environnement détectées et de paramètres de prédiction (P), une situation de circulation routière (PU) du véhicule (2) est prédite pour un instant à venir. Selon la présente invention, lorsque l'instant à venir est atteint, une situation de circulation routière actuelle réelle est détectée, la situation de circulation routière actuelle réelle est comparée à la situation de circulation routière prédite et il est déterminé dans la comparaison si une erreur de prédiction était présente dans la prédiction. En cas de présence d'une erreur de prédiction, les paramètres de prédiction (P) sont corrigés. La présente invention concerne en outre un procédé de fonctionnement d'un véhicule (2) à conduite automatisée, en particulier à conduite très automatisée ou autonome.
PCT/EP2020/057501 2019-04-16 2020-03-18 Procédé de prédiction d'une situation de circulation routière pour un véhicule WO2020212061A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US17/602,354 US11945450B2 (en) 2019-04-16 2020-03-18 Method for predicting a traffic situation for a vehicle
CN202080029414.0A CN113728369B (zh) 2019-04-16 2020-03-18 用于预测车辆的交通状况的方法

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102019002790.6 2019-04-16
DE102019002790.6A DE102019002790B4 (de) 2019-04-16 2019-04-16 Verfahren zur Prädiktion einer Verkehrssituation für ein Fahrzeug

Publications (1)

Publication Number Publication Date
WO2020212061A1 true WO2020212061A1 (fr) 2020-10-22

Family

ID=69941369

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2020/057501 WO2020212061A1 (fr) 2019-04-16 2020-03-18 Procédé de prédiction d'une situation de circulation routière pour un véhicule

Country Status (4)

Country Link
US (1) US11945450B2 (fr)
CN (1) CN113728369B (fr)
DE (1) DE102019002790B4 (fr)
WO (1) WO2020212061A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022217495A1 (fr) * 2021-04-14 2022-10-20 华为技术有限公司 Procédé et dispositif de commande de véhicule et véhicule

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102020129451A1 (de) 2020-11-09 2022-05-12 Audi Ag Verfahren zur Prädiktion von Fahreingriffen, Verfahren zum Training eines Algorithmus und Kraftfahrzeug
DE102021205067A1 (de) 2021-05-19 2022-11-24 Zf Friedrichshafen Ag Fahrzeugsystem zur Fehlererkennung in einem Umfeldmodell und Fahrzeug
DE102022205174A1 (de) * 2022-05-24 2023-11-30 Psa Automobiles Sa Kollektive Informationsbeschaffung für automatisierte Fahrsteuerfunktionen
DE102022002457A1 (de) 2022-07-05 2024-01-11 Mercedes-Benz Group AG Verfahren zur Prädiktion eines Einflusses eines Verkehrsteilnehmers auf zumindest einen anderen Verkehrsteilnehmer und Verfahren zum Betrieb eines Fahrzeugs
CN117915292A (zh) * 2022-10-10 2024-04-19 索尼集团公司 电子设备、通信方法和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6442453B1 (en) * 1999-10-08 2002-08-27 Hitachi, Ltd. Vehicle-traveling supporting system
US20050012604A1 (en) * 2003-07-08 2005-01-20 Nissan Motor Co., Ltd. Vehicle obstacle detecting device
DE102012005272A1 (de) 2012-02-20 2012-10-25 Daimler Ag Verfahren zur Ermittlung einer Gefahrenwahrscheinlichkeit und Verwendung des Verfahrens
US20180374359A1 (en) * 2017-06-22 2018-12-27 Bakhi.com Times Technology (Beijing) Co., Ltd. Evaluation framework for predicted trajectories in autonomous driving vehicle traffic prediction
DE102017212629A1 (de) * 2017-07-24 2019-01-24 Bayerische Motoren Werke Aktiengesellschaft Prädiktion des Verhaltens eines Verkehrsteilnehmers
DE102018008024A1 (de) * 2018-10-10 2019-04-11 Daimler Ag Verfahren zur Bewertung einer Verkehrssituation

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3225203B2 (ja) * 1996-05-07 2001-11-05 小糸工業株式会社 駐車場利用状況予測装置及び駐車場利用状況測定装置、並びにこれらを用いた駐車場案内装置
JPH10312497A (ja) * 1997-05-13 1998-11-24 Toshiba Corp 交通状況予測装置
DE19856704C2 (de) * 1998-12-09 2001-09-13 Daimler Chrysler Ag Verfahren und Vorrichtung zur Fahrzeugzielführung und/oder Reisezeitschätzung
DE19904909C2 (de) * 1999-02-06 2003-10-30 Daimler Chrysler Ag Verfahren und Vorrichtung zur Bereitstellung von Verkehrsinformationen
DE10062856B4 (de) * 2000-12-16 2008-01-10 Daimlerchrysler Ag Verfahren zur fahrzeugindividuellen Verkehrsprognose
JP4055656B2 (ja) 2003-05-30 2008-03-05 トヨタ自動車株式会社 衝突予測装置
DE102011101359A1 (de) 2011-05-12 2012-11-15 GM Global Technology Operations LLC (n. d. Gesetzen des Staates Delaware) Verfahren und Vorrichtung zur Klassifikation von Daten
DE102011083677A1 (de) * 2011-09-29 2013-04-04 Bayerische Motoren Werke Aktiengesellschaft Prognose einer Verkehrssituation für ein Fahrzeug
CN103116808A (zh) * 2013-01-18 2013-05-22 同济大学 一种快速路短时交通流实时预测的方法
DE102013214225A1 (de) * 2013-07-19 2015-01-22 Bayerische Motoren Werke Aktiengesellschaft Dynamische Neuplanung einer Fahrtrajektorie mittels LQ-Regelung für einen Ausweichassistenten
CN104504897B (zh) * 2014-09-28 2017-10-31 北京工业大学 一种基于轨迹数据的交叉口交通流特性分析及车辆运动预测方法
EP3091509A1 (fr) * 2015-05-04 2016-11-09 Honda Research Institute Europe GmbH Procédé pour améliorer les performances d'un procédé de prédiction par calcul de l'état futur d'un objet cible, système d'assistance au conducteur, véhicule équipé d'un tel système d'assistance au conducteur et support de stockage de programme correspondant et programme
DE102016000493B4 (de) 2016-01-19 2017-10-19 Audi Ag Verfahren zum Betrieb eines Fahrzeugsystems und Kraftfahrzeug
JP6704583B2 (ja) 2016-12-27 2020-06-03 株式会社デンソーアイティーラボラトリ 学習システムおよび学習方法
CN107264534B (zh) * 2017-05-23 2019-07-09 北京理工大学 基于驾驶员经验模型的智能驾驶控制系统和方法、车辆
DE102017216202A1 (de) * 2017-09-13 2019-03-14 Bayerische Motoren Werke Aktiengesellschaft Verfahren zur Prädiktion einer optimalen Fahrspur auf einer mehrspurigen Straße

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6442453B1 (en) * 1999-10-08 2002-08-27 Hitachi, Ltd. Vehicle-traveling supporting system
US20050012604A1 (en) * 2003-07-08 2005-01-20 Nissan Motor Co., Ltd. Vehicle obstacle detecting device
DE102012005272A1 (de) 2012-02-20 2012-10-25 Daimler Ag Verfahren zur Ermittlung einer Gefahrenwahrscheinlichkeit und Verwendung des Verfahrens
US20180374359A1 (en) * 2017-06-22 2018-12-27 Bakhi.com Times Technology (Beijing) Co., Ltd. Evaluation framework for predicted trajectories in autonomous driving vehicle traffic prediction
DE102017212629A1 (de) * 2017-07-24 2019-01-24 Bayerische Motoren Werke Aktiengesellschaft Prädiktion des Verhaltens eines Verkehrsteilnehmers
DE102018008024A1 (de) * 2018-10-10 2019-04-11 Daimler Ag Verfahren zur Bewertung einer Verkehrssituation

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022217495A1 (fr) * 2021-04-14 2022-10-20 华为技术有限公司 Procédé et dispositif de commande de véhicule et véhicule

Also Published As

Publication number Publication date
US20220169262A1 (en) 2022-06-02
CN113728369A (zh) 2021-11-30
DE102019002790B4 (de) 2023-05-04
CN113728369B (zh) 2023-04-04
DE102019002790A1 (de) 2020-08-06
US11945450B2 (en) 2024-04-02

Similar Documents

Publication Publication Date Title
DE102019002790B4 (de) Verfahren zur Prädiktion einer Verkehrssituation für ein Fahrzeug
EP3181422B1 (fr) Procédé et système de commande automatique d'un véhicule suiveur comprenant un véhicule scout
EP3181423B1 (fr) Procédé et système de commande automatique d'un véhicule suiveur comprenant un véhicule scout
DE102013019424B4 (de) Verfahren zum Betrieb eines Fahrzeugsystems zur Überwachung eines Fahrers und Kraftfahrzeug
DE102017217444B4 (de) Verfahren und System zum Aktualisieren eines Steuerungsmodells für eine automatische Steuerung zumindest einer mobilen Einheit
WO2018145951A1 (fr) Procédé de coordination d'un trafic de plusieurs véhicules dans une zone d'infrastructure prédéterminée ainsi que dispositif serveur, véhicule automobile et système
DE102019002487A1 (de) Verfahren zur Überprüfung eines Umfelderfassungssensors eines Fahrzeugs und Verfahren zum Betrieb eines Fahrzeugs
DE102016007563A1 (de) Verfahren zur Trajektorienplanung
DE102018210779A1 (de) Verfahren und System zur Rettungsgassenbildung durch ein Fahrzeug
WO2020048684A1 (fr) Procédé de fonctionnement sans conducteur d'un véhicule
DE102019214448A1 (de) Verfahren zum Assistieren eines Kraftfahrzeugs
DE102021201130A1 (de) Verfahren zum infrastrukturgestützten Assistieren mehrerer Kraftfahrzeuge
EP4288954A1 (fr) Procédé d'aide à l'infrastructure d'un véhicule à moteur
WO2020119987A1 (fr) Procédé pour fournir des données cartographiques d'une carte numérique et un itinéraire
DE102018214506A1 (de) Verfahren zur Weiterentwicklung eines Fahrerassistenzsystems und Fahrerassistenzsystem für ein Fahrzeug
DE102021207456A1 (de) Verfahren zum zumindest teilautomatisierten Führen eines Kraftfahrzeugs
WO2022122250A1 (fr) Procédé assisté par infrastructure de détermination de trajectoires pour véhicules autonomes
DE102017221634B4 (de) Kraftfahrzeug mit einem Fahrzeugführungssystem, Verfahren zum Betrieb eines Fahrzeugführungssystems und Computerprogramm
DE102021201129A1 (de) Vorrichtung zum infrastrukturgestützten Assistieren eines Kraftfahrzeugs
EP4301644B1 (fr) Procédé de détermination et de délivrance d'une vitesse de déplacement adaptée à une situation de conduite
DE112022002031T5 (de) Bordinformationsverarbeitungsvorrichtung, system für autonomes fahren und bordsystem
EP4211910A1 (fr) Procédé pour guider un véhicule automobile
DE102022002869A1 (de) Verfahren zur Bestimmung der Verfügbarkeit von Ladestationen
DE102021113767A1 (de) Überwachungseinrichtung und Verfahren zum Überwachen eines Gesamtsystems aus mehreren unterschiedlichen Teilsystemen auf Fehler und Kraftfahrzeug
DE102021209431A1 (de) Verfahren zum zumindest teilautomatisierten Führen eines Kraftfahrzeugs

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20713251

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20713251

Country of ref document: EP

Kind code of ref document: A1